Heart disease is one of the main causes of death in the modern world. Cardiovascular disease prediction is a major issue in clinical data analysis. While accurately forecasting heart illness is a challenging task, contemporary Machine Learning (ML) techniques make it feasible. By putting in place a strong machine learning system, cardiovascular illnesses can be accurately predicted, human intervention can be reduced, and supplementary medical tests may be avoided. The severity and death rate of the condition can be decreased with this kind of evaluation. Few research demonstrate how machine learning methods might be used to predict heart disease. This research presents a hybrid method (Support Vector Machine and Decision Tree) for utilizing Machine Learning (ML) approaches to increase the accuracy of cardiovascular disease prediction. The prediction model is introduced using famous categorization algorithms and a multitude of feature combinations. A mixed machine learning (ML) prediction model for heart disease offers higher accuracy and better performance.

Heart Disease prediction; Cardiovascular Disease Prediction; Naïve Bayes (NB); Machine Learning (ML); Support Vector Machine (SVM).